Incremental Blockwise Beam Search for Simultaneous Speech Translation with Controllable Quality-Latency Tradeoff

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F23%3A10475953" target="_blank" >RIV/00216208:11320/23:10475953 - isvavai.cz</a>

Result on the web

<a href="https://doi.org/10.21437/Interspeech.2023-2225" target="_blank" >https://doi.org/10.21437/Interspeech.2023-2225</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.21437/Interspeech.2023-2225" target="_blank" >10.21437/Interspeech.2023-2225</a>

Result language

angličtina

Original language name

Incremental Blockwise Beam Search for Simultaneous Speech Translation with Controllable Quality-Latency Tradeoff

Original language description

Blockwise self-attentional encoder models have recently emerged as one promising end-to-end approach to simultaneous speech translation. These models employ a blockwise beam search with hypothesis reliability scoring to determine when to wait for more input speech before translating further. However, this method maintains multiple hypotheses until the entire speech input is consumed - this scheme cannot directly show a single incremental translation to users. Further, this method lacks mechanisms for controlling the quality vs. latency tradeoff. We propose a modified incremental blockwise beam search incorporating local agreement or hold-n policies for quality-latency control. We apply our framework to models with limited and full-context encoders, with the latter demonstrating that offline models can be effectively converted to online models. Experimental results on MuST-C show 0.6-3.6 BLEU improvement without changing latency or 0.8-1.4 s latency improvement without changing quality.

Czech name

—

Czech description

—

Type

D - Article in proceedings

CEP classification

—

OECD FORD branch

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Project

<a href="/en/project/GX19-26934X" target="_blank" >GX19-26934X: Neural Representations in Multi-modal and Multi-lingual Modeling</a><br>

Continuities

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Publication year

2023

Confidentiality

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Article name in the collection

Proceedings of the 24st Annual Conference of the International Speech Communication Association

ISBN

—

ISSN

1990-9772

e-ISSN

—

Number of pages

5

Pages from-to

3979-3983

Publisher name

International Speech Communication Association

Place of publication

Baixas, France

Event location

Dublin, Ireland

Event date

Aug 20, 2023

Type of event by nationality

WRD - Celosvětová akce

UT code for WoS article

—